Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20805
    Prev
    Next
    INDEX
    Explanations

    phrases related to impact or influence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nationwide
    -0.67
    ļéĨĴ
    -0.65
    geries
    -0.65
     Jed
    -0.64
    WHO
    -0.63
     Barney
    -0.63
    noon
    -0.62
    inav
    -0.62
     Reloaded
    -0.61
     Comcast
    -0.60
    POSITIVE LOGITS
     spawned
    0.88
     inhabit
    0.86
     occupant
    0.84
     inhab
    0.84
     deems
    0.83
     entails
    0.78
     encountered
    0.77
     wearer
    0.76
     respective
    0.73
     performs
    0.73
    Activations Density 0.197%

    No Known Activations